Automated Data Quality Control in FDOPA brain PET Imaging using Deep Learning.

INTRODUCTION: With biomedical imaging research increasingly using large datasets, it becomes critical to find operator-free methods to quality control the data collected and the associated analysis. Attempts to use artificial intelligence (AI) to perform automated quality control (QC) for both single-site and multi-site datasets have been explored in some neuroimaging techniques (e.g. EEG or MRI), although these methods struggle to find replication in other domains. The aim of this study is to test the feasibility of an automated QC pipeline for brain [18F]-FDOPA PET imaging as a biomarker for the dopamine system. METHODS: Two different Convolutional Neural Networks (CNNs) were used and combined to assess spatial misalignment to a standard template and the signal-to-noise ratio (SNR) relative to 200 static [18F]-FDOPA PET images that had been manually quality controlled from three different PET/CT scanners. The scans were combined with an additional 400 scans, in which misalignment (200 scans) and low SNR (200 scans) were simulated. A cross-validation was performed, where 80% of the data were used for training and 20% for validation. Two additional datasets of [18F]-FDOPA PET images (50 and 100 scans respectively with at least 80% of good quality images) were used for out-of-sample validation. RESULTS: The CNN performance was excellent in the training dataset (accuracy for motion: 0.86 ± 0.01, accuracy for SNR: 0.69 ± 0.01), leading to 100% accurate QC classification when applied to the two out-of-sample datasets. Data dimensionality reduction affected the generalizability of the CNNs, especially when the classifiers were applied to the out-of-sample data from 3D to 1D datasets. CONCLUSIONS: This feasibility study shows that it is possible to perform automatic QC of [18F]-FDOPA PET imaging with CNNs. The approach has the potential to be extended to other PET tracers in both brain and non-brain applications, but it is dependent on the availability of large datasets necessary for the algorithm training.

Alzheimer's Disease: A Step Towards Prognosis Using Smart Wearables †.

Alzheimer's disease (AD) is the most common cause of dementia. Several haemodynamic risk factors for AD have been identified, including ageing, increased arterial stiffness, high systolic blood pressure (BP) and brain hypoperfusion. We propose a novel approach for assessing haemodynamic risk factors by analysing arterial pulse waves (PWs). The aim of this feasibility study was to determine whether features extracted from PWs measured by wearable sensors might have utility for stratifying patients at risk of AD. A numerical model of PW propagation was used to simulate PWs for virtual subjects of each age decade from 25 to 75 years (16 subjects in total), with subjects at each age exhibiting normal variation in arterial stiffness. Several PW features were extracted, and their relationships with AD risk factors were investigated. PWs at the wrist were found to exhibit changes with age and arterial stiffness, indicating that it may be possible to identify changes in risk factors from smart wearables. Several candidate PW features were identified which changed significantly with age for future testing. This study demonstrates the potential feasibility of assessing haemodynamic risk factors for AD from non-invasive PWs. These factors could be assessed from the PPG PW, which can be acquired by smart watches and phones. If the findings are replicated in clinical studies, then this may provide opportunities for patients to assess their own risk and make lifestyle changes accordingly.